mlsanityData to 7 Oct 2026

Nested Variational Inference

arXiv 2106.11302 ↗First posted 21 Jun 2021stat.ML cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each level of nesting. NVI is applicable to many commonly-used importance sampling strategies and provides a mechanism for learning intermediate densities, which can serve as heuristics to guide the sampler. Our experiments apply NVI to (a) sample from a multimodal distribution using a learned annealing path (b) learn heuristics that approximate the likelihood of future observations in a hidden Markov model and (c) to perform amortized inference in hierarchical deep generative models. We observe that optimizing nested objectives leads to improved sample quality in terms of log average weight and effective sample size.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

35 of 56 references.

References · 35

  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2015Importance Weighted Autoencoderscited by 454
  3. 2013Black Box Variational Inferencecited by 317
  4. 2018Neural Importance Samplingcited by 154
  5. 2015Gradient Estimation Using Stochastic Computation Graphscited by 120
  6. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  7. 2017Variational Sequential Monte Carlocited by 93
  8. 2017Filtering Variational Objectivescited by 91
  9. 2021Annealed Flow Transport Monte Carlocited by 90
  10. 2018Tighter Variational Bounds are Not Necessarily Bettercited by 76
  11. 2014Reweighted Wake-Sleepcited by 66
  12. 2017Auto-Encoding Sequential Monte Carlocited by 64
23 more
  1. 2019Elements of Sequential Monte Carlocited by 60
  2. 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
  3. 2018Hamiltonian Variational Auto-Encodercited by 41
  4. 2018Doubly Reparameterized Gradient Estimators for Monte Carlo Objectivescited by 41
  5. 2019The continuous Bernoulli: fixing a pervasive error in variational autoencoderscited by 40
  6. 2013Automated Variational Inference in Probabilistic Programmingcited by 31
  7. 2019The Thermodynamic Variational Objectivecited by 26
  8. 2018Improving Explorability in Variational Inference with Annealed Variational Objectivescited by 24
  9. 2015A New Approach to Probabilistic Programming Inferencecited by 22
  10. 2016Deep Amortized Inference for Probabilistic Programscited by 22
  11. 2017Approximate Inference with Amortised MCMCcited by 22
  12. 2020Automatic structured variational inferencecited by 21
  13. 2015Nested Sequential Monte Carlo Methodscited by 19
  14. 2016Variational Inference with Hamiltonian Monte Carlocited by 17
  15. 2021Generalized Doubly Reparameterized Gradient Estimatorscited by 14
  16. 2018Automated learning with a probabilistic programming language: Birchcited by 11
  17. 2016Interacting Particle Markov Chain Monte Carlocited by 6
  18. 2019Amortized Population Gibbs Samplers with Neural Sufficient Statisticscited by 6
  19. 2021Learning Proposals for Probabilistic Programs with Inference Combinatorscited by 6
  20. 2014Sequential Monte Carlo for Graphical Modelscited by 4
  21. 2015Particle Gibbs with Ancestor Sampling for Probabilistic Programscited by 3
  22. 2016Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networkscited by 2
  23. 2021Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Seriescited by 1

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 2; 2024: 5; 2025: 2.

14 papers.

Sort:

  1. 2022GFlowNets and variational inferencecited by 103
  2. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  3. 2022A Variational Perspective on Generative Flow Networkscited by 39
  4. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  5. 2022Recursive Monte Carlo and Variational Inference with Auxiliary Variablescited by 8
  6. 2024Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inferencecited by 7
  7. 2025Bridge the Inference Gaps of Neural Processes via Expectation Maximizationcited by 7
  8. 2022Black-box Coreset Variational Inferencecited by 4
  9. 2023NAS-X: Neural Adaptive Smoothing via Twistingcited by 4
  10. 2024Probabilistic Programming with Programmable Variational Inferencecited by 4
  11. 2024GFlowNet Training by Policy Gradientscited by 4
  12. 2024VISA: Variational Inference with Sequential Sample-Average Approximationscited by 1
2 more
  1. 2024Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AIcited by 0
  2. 2025Revisiting Unbiased Implicit Variational Inferencecited by 0